Presentation is loading. Please wait.

Presentation is loading. Please wait.

Query Evaluation Techniques for Cluster Database Systems Andrey V. Lepikhov, Leonid B. Sokolinsky South Ural State University Russia 22 September 2010.

Published by Modified over 9 years ago

Similar presentations

Presentation on theme: "Query Evaluation Techniques for Cluster Database Systems Andrey V. Lepikhov, Leonid B. Sokolinsky South Ural State University Russia 22 September 2010."— Presentation transcript:

1 Query Evaluation Techniques for Cluster Database Systems Andrey V. Lepikhov, Leonid B. Sokolinsky South Ural State University Russia 22 September 2010 1 ADBIS 2010

2 Outline 22 September 2010 ADBIS 20102  Motivation  Problem Statement  Background  Partial mirroring method  Results  Future work

3 Motivation 22 September 2010 3 Top500 Cluster: 84.8% MPP: 14.8% Others: 0.4% ADBIS 2010

4 Problem Statement 22 September 2010 4  Not expensive parallel hardware needs not expensive parallel database management system  Today we have no such chip parallel database management system ADBIS 2010

5 Background 22 September 2010 5ADBIS 2010

6 Exchange operator 22 September 2010 ADBIS 20106  p: port  ψ : distributing function

7 Parallel plan for query Q = R  S 22 September 2010 ADBIS 20107

8 Query processing in cluster system 22 September 2010 8ADBIS 2010

9 The problem 22 September 2010 ADBIS 20109  Load balancing

10 Partial mirroring method  Fragmentation strategy  Replication strategy 10

11 Fragmentation strategy 22 September 2010 ADBIS 201011 FRAGMENTATION  Source relation P0P0 P1P1 PnPn Relation is divided into fragments distributed among cluster nodes Each fragment is divided into sequence of segments with an equal length Segment is the minimal unit of replication...

12 Replication strategy 22 September 2010 ADBIS 201012 Disk D i Disk D j ρ j = 50% RiRi

13 Load balancing method 22 September 2010 ADBIS 201013 D1D1 D2D2 t1t1 D1D1 D2D2 t2t2 D1D1 D2D2 - scheduled to process D1D1 D2D2 t4t4 - processed t3t3 P1P1 P2P2 P1P1 P2P2 P1P1 P1P1 P2P2 P2P2 - not used

14 Parallel agent with two input streams 22 September 2010 ADBIS 201014

15 Load balancing algorithm 22 September 2010 ADBIS 201015

16 Parameters of experiments 22 September 2010 ADBIS 201016

17 Speedup versus replication factor 22 September 2010 ADBIS 201017

18 Speedup versus skew factor θ 22 September 2010 ADBIS 201018 0.68 corresponds to the ”80-20” rule (80 percents of tuples of the relation will be stored in 20 percents of fragments) 0 corresponds to the uniform distribution

19 Future Work 22 September 2010 ADBIS 201019  To incorporate the proposed technique of parallel query execution into open source PostgreSQL DBMS.  To extend this approach on GRID DBMS for clusters with multicor processors.

20 22 September 2010 ADBIS 201020  Thank you

Download ppt "Query Evaluation Techniques for Cluster Database Systems Andrey V. Lepikhov, Leonid B. Sokolinsky South Ural State University Russia 22 September 2010."

Similar presentations

Distributed DBMS©M. T. Özsu & P. Valduriez Ch.14/1 Outline Introduction Background Distributed Database Design Database Integration Semantic Data Control.

Distributed DBMS©M. T. Özsu & P. Valduriez Ch.14/1 Outline Introduction Background Distributed Database Design Database Integration Semantic Data Control.
Revisiting Co-Processing for Hash Joins on the Coupled CPU- GPU Architecture School of Computer Engineering Nanyang Technological University 27 th Aug.

Revisiting Co-Processing for Hash Joins on the Coupled CPU- GPU Architecture School of Computer Engineering Nanyang Technological University 27 th Aug.
Dependence Precedence. Precedence & Dependence Can we execute a 1000 line program with 1000 processors in one step? What are the issues to deal with in.

Dependence Precedence. Precedence & Dependence Can we execute a 1000 line program with 1000 processors in one step? What are the issues to deal with in.
Query Task Model (QTM): Modeling Query Execution with Tasks 1 Steffen Zeuch and Johann-Christoph Freytag.

Query Task Model (QTM): Modeling Query Execution with Tasks 1 Steffen Zeuch and Johann-Christoph Freytag.
LIBRA: Lightweight Data Skew Mitigation in MapReduce

LIBRA: Lightweight Data Skew Mitigation in MapReduce
T h e G a s L a w s. T H E G A S L A W S z B o y l e ‘ s L a w z D a l t o n ‘ s L a w z C h a r l e s ‘ L a w z T h e C o m b i n e d G a s L a w z B.

T h e G a s L a w s. T H E G A S L A W S z B o y l e ‘ s L a w z D a l t o n ‘ s L a w z C h a r l e s ‘ L a w z T h e C o m b i n e d G a s L a w z B.
Fall 2008Parallel Query Optimization1. Fall 2008Parallel Query Optimization2 Bucket Sizes and I/O Costs Bucket B does not fit in the memory in its entirety,

Fall 2008Parallel Query Optimization1. Fall 2008Parallel Query Optimization2 Bucket Sizes and I/O Costs Bucket B does not fit in the memory in its entirety,
Efficient Processing Regular Queries In Shared-Nothing Parallel Database Systems Using Tree- And Structural Indexes (ADBIS 2007, Bulgaria) Vu Le Anh, Attilla.

Efficient Processing Regular Queries In Shared-Nothing Parallel Database Systems Using Tree- And Structural Indexes (ADBIS 2007, Bulgaria) Vu Le Anh, Attilla.
Development of Parallel Simulator for Wireless WCDMA Network Hong Zhang Communication lab of HUT.

Development of Parallel Simulator for Wireless WCDMA Network Hong Zhang Communication lab of HUT.
Parallel Database Systems

Parallel Database Systems
Parallel Database Systems The Future Of High Performance Database Systems David Dewitt and Jim Gray 1992 Presented By – Ajith Karimpana.

Parallel Database Systems The Future Of High Performance Database Systems David Dewitt and Jim Gray 1992 Presented By – Ajith Karimpana.
Query Execution Professor: Dr T.Y. Lin Prepared by, Mudra Patel Class id: 113.

Query Execution Professor: Dr T.Y. Lin Prepared by, Mudra Patel Class id: 113.
1 One Torus to Rule Them All: Multi-dimensional Queries in P2P Systems Prasanna Ganesan Beverly Yang Hector Garcia-Molina Stanford University.

1 One Torus to Rule Them All: Multi-dimensional Queries in P2P Systems Prasanna Ganesan Beverly Yang Hector Garcia-Molina Stanford University.
1 Minggu 12, Pertemuan 23 Introduction to Distributed DBMS (Chapter 22.1-4, 22.6, 3rd ed.) Matakuliah: T0206-Sistem Basisdata Tahun: 2005 Versi: 1.0/0.0.

1 Minggu 12, Pertemuan 23 Introduction to Distributed DBMS (Chapter , 22.6, 3rd ed.) Matakuliah: T0206-Sistem Basisdata Tahun: 2005 Versi: 1.0/0.0.
Optimization and evaluation of parallel I/O in BIPS3D parallel irregular application Performance Modelling, Evaluation, and optimization of Parallel and.

Optimization and evaluation of parallel I/O in BIPS3D parallel irregular application Performance Modelling, Evaluation, and optimization of Parallel and.
1 Distributed Databases CS347 Lecture 14 May 30, 2001.

1 Distributed Databases CS347 Lecture 14 May 30, 2001.
VLDB 20051 Revisiting Pipelined Parallelism in Multi-Join Query Processing Bin Liu and Elke A. Rundensteiner Worcester Polytechnic Institute

VLDB Revisiting Pipelined Parallelism in Multi-Join Query Processing Bin Liu and Elke A. Rundensteiner Worcester Polytechnic Institute
Scheduling with Optimized Communication for Time-Triggered Embedded Systems Slide 1 Scheduling with Optimized Communication for Time-Triggered Embedded.

Scheduling with Optimized Communication for Time-Triggered Embedded Systems Slide 1 Scheduling with Optimized Communication for Time-Triggered Embedded.
Flow Algorithms for Two Pipelined Filtering Problems Anne Condon, University of British Columbia Amol Deshpande, University of Maryland Lisa Hellerstein,

Flow Algorithms for Two Pipelined Filtering Problems Anne Condon, University of British Columbia Amol Deshpande, University of Maryland Lisa Hellerstein,
Science Advisory Committee Meeting - 20 September 3, 2010 Stanford University 1 04_Parallel Processing Parallel Processing Majid AlMeshari John W. Conklin.

Science Advisory Committee Meeting - 20 September 3, 2010 Stanford University 1 04_Parallel Processing Parallel Processing Majid AlMeshari John W. Conklin.

Similar presentations

Ads by Google